Silk Design logo

Silk Design

Community
bendrape1-byte
silk-design

Build websites and web UI with smooth, polished, high-end motion by default — the buttery feel of premium sites, not static slop. Use when building or restyling any website, landing page, hero, marketing page, portfolio, or web UI; when adding scroll animations, reveals, parallax, marquees, hover effects, page transitions, smooth scrolling, or micro-interactions; or when a page feels flat, generic, or unrefined and needs to feel alive. A capability catalog of proven motion + smoothness + design-token techniques (Lenis, Framer Motion, GSAP, Tailwind v4) for interfaces that feel crafted rather than assembled.

Overview

Publisherbendrape1-byte
Repositorysilk-design
Skill namesilk-design
Stars
140
Forks
6
Bundled files
48
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 48 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bendrape1-byte on GitHub. Read the source before you install it.

Installation

Install the Silk Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bendrape1-byte/silk-design/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bendrape1-byte/silk-design.git \
  .claude/skills/silk-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Silk Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Silk Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Silk Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

silk — your web-craft toolbox

This is a reminder of what you can do. Like an artist who knows their tools: when you build for the web, you are not limited to static sections and default scrollbars. You have a full palette of motion and smoothness that reads as "expensive." Reach for it by default.

The rule: never ship a static page. A smooth-scroll root + a reveal-on-scroll + one signature effect is ~15 lines and turns generic output into something that feels crafted. The trick behind these sites isn't exotic code — it's a small, consistent set of levers applied everywhere. Consistency is what reads as clean.

Stack this assumes

React + Vite + Tailwind v4 + motion (Framer Motion, motion/react) + GSAP (gsap + @gsap/react; plugins used: ScrollTrigger, Draggable, DrawSVGPlugin — all free) + Lenis (smooth scroll). Each technique below names its principle so it transfers to other stacks. cls()/cn() helpers → assets/utils.ts.

The non-negotiable foundation (apply on EVERY build)

This is the baseline that makes everything feel smooth. Four things, always:

  1. Lenis smooth scroll at the root. Wrap the app once. Do not use CSS scroll-behavior.
    tsx
    import { ReactLenis } from 'lenis/react'
    <ReactLenis root>{app}</ReactLenis>
    Anchor links scroll via useLenis().scrollTo(el) — see assets/useButtonClick.ts.
  2. Kill scroll bounce + thin the scrollbar in global CSS:
    css
    html, body { overscroll-behavior: none; }
    * { scrollbar-width: thin; scrollbar-color: rgb(0 0 0 / 0.3) transparent; }
  3. Token architecture — ~9 CSS custom properties on :root, exposed to Tailwind via @theme inline, with ONE --radius driving the whole radius scale. Full recipe + verbatim example in assets/foundation.css and references/design-system.md.
  4. Fluid typography — every font size is a clamp(min, vw, max), not a fixed px. This is why the type scales smoothly across viewports. Scale in assets/foundation.css.

The one reveal config, used everywhere (this consistency is the "clean" feel):

tsx
initial="hidden" whileInView="visible"
viewport={{ once: true, margin: "-20%" }}
transition={{ duration: 0.6, ease: "easeOut" }}   // text: staggerChildren 0.04, per-word 0.6

Drop-in components: assets/ScrollReveal.tsx (blocks), assets/TextAnimation.tsx (word-stagger headings).

The toolbox map — reach for these

Each points to a reference file (loaded only when you need it) and/or a drop-in assets/ file.

  • Entrance reveals — word-stagger headings, slide-up / fade-blur blocks. → references/effects.md, assets/{TextAnimation,ScrollReveal}.tsx
  • Scroll-driven effects — parallax (useScroll/useTransform), hero exit-parallax, pinned + scrubbed sections, scroll-scrubbed video, tilt-flatten billboard, stack-to-grid (FLIP), reading word-fill, footer reveal-from-behind. → references/effects.md, assets/{HeroVideoScroll,AboutTextFill,FooterBrandReveal}.tsx
  • Cursor & pointer — GSAP cursor image-trail, magnetic buttons (spring 150/15), pointer-tracked border glow, cursor-mask character pattern, draggable stickers. → references/effects.md, assets/{AboutCursorTrail,ButtonMagnetic,BorderGlow,HoverPattern}.tsx
  • Hover micro-interactions — 12 button styles (expand, elastic, flip, slide, bounce…), the grid-fr expand-to-auto trick, image reveal cards, 3D flip cards, staged hover scenes. → references/effects.md
  • Marquees & carousels — infinite CSS scroll with edge-mask fade, deck carousel, focus loop, filter-swap. → references/effects.md, assets/{animations,masks}.css
  • Navigation & page transitions — fullscreen curtain menu, DrawSVG swirl page transition, brand panel loader. → references/effects.md, assets/{NavbarFullscreen,PageTransitionSwirl}.tsx
  • Animated backgrounds — 13 of them: aurora, light rays, gradient bars, noise, grids, floating gradients. → references/backgrounds.md, assets/{AuroraBackground,NoiseBackground,GradientBarsBackground}.tsx
  • The design system — token architecture, fluid type, --radius scale, font pairings + the accent-font slot, full-width wordmarks (assets/AutoFillText.tsx), and 10 instant "style" skins (glass, minimal, neon, elegant, bold…) = swap only card CSS + button CSS + radius + font. → references/design-system.md
  • Page composition — section archetypes (hero/features/testimonial/pricing/faq/CTA), the canonical section-header pattern, bento live-widget menu, navbar archetypes, responsive-padding scale, how to assemble a page. → references/composition.md

Reference a worked example — /silk-design <name>

The catalog carries 23 worked reference compositions built from this exact toolbox. When the user names one (/silk-design Reference15, /silk-design Reference1, or "build it like the coffee one"), pull it from references/templates.md — palette, font, section rhythm, and the signature effects it used. A number resolves directly; a described mood resolves against each row's vibe line. A referenced composition is a mood-board + wireframe, not a source file: take its skin (palette, font, radius, card/button style, effects) and its skeleton (section rhythm, loosely) — never its flesh (copy, images, brand, or a 1:1 layout). The new site has its own subject; build for that. The non-negotiable foundation above still applies underneath.

Using the assets/ files

They are drop-in reference implementations — copy and adapt. Simple primitives (ScrollReveal, TextAnimation, ButtonMagnetic, AutoFillText, BorderGlow, HoverPattern, PageTransitionSwirl, useButtonClick, utils, the .css) drop in cleanly. The section showpieces (AboutCursorTrail, HeroVideoScroll, AboutTextFill, FooterBrandReveal, NavbarFullscreen) are self-contained and take an actions slot — pass your own buttons in as children rather than wiring a component import. Backgrounds need the --color-* tokens from foundation.css. (FooterBrandReveal needs AutoFillText — both are here.)

How this fits with your other skills

This is a capability layer, not a builder. For aesthetic direction (palette, layout, personality) reach for taste-skill (landing/marketing/portfolio) or ui-ux-pro-max (apps/dashboards/data UI). silk is what you apply on top — or to any hand-built page — to make it move and feel right. The three compose: builder picks the look, silk makes it silk.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Silk Design AI skill do?

Build websites and web UI with smooth, polished, high-end motion by default — the buttery feel of premium sites, not static slop. Use when building or restyling any website, landing page, hero, marketing page, portfolio, or web UI; when adding scroll animations, reveals, parallax, marquees, hover effects, page transitions, smooth scrolling, or micro-interactions; or when a page feels flat, generic, or unrefined and needs to feel alive. A capability catalog of proven motion + smoothness + design-token techniques (Lenis, Framer Motion, GSAP, Tailwind v4) for interfaces that feel crafted rathe...

Why use Silk Design on TypingMind?

Because you install it once and use it with any model. Silk Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Silk Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bendrape1-byte/silk-design/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Silk Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Silk Design?

As many as you like. As long as a model supports skills, you can use Silk Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Silk Design AI skill free?

Yes. It is published on GitHub by bendrape1-byte under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇